23CS1503 ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING TECHNIQUES 

COURSE OBJECTIVES:

● To understand the various characteristics of intelligent agents

● To learn the different search strategies in AI 

● To learn to represent knowledge in solving AI problems

● To know about the various applications of AI 

● To understand the need for machine learning and various algorithms in machine learning. 

 UNIT I               INTRODUCTION                                                                                        9 

Introduction–Definition – Future of Artificial Intelligence – Characteristics of Intelligent Agents–Typical Intelligent Agents – Problem Solving Approach to Typical AI problemsSearch Strategies- Uninformed – Informed-BFS-Greedy best first search-A* search . 

UNIT II             PROBLEM SOLVING METHODS                                                                 9 

Problem solving Methods – Heuristics - Iterative Deepening A*- RBFS – Memory Bounded A* – Local Search Algorithms and Optimization Problems - Searching with Partial Observations – Constraint Satisfaction Problems – Constraint Propagation – Backtracking Search – Game Playing –Min Max- Optimal Decisions in Games – Alpha Beta Pruning – Stochastic Games 

UNIT III KNOWLEDGE REPRESENTATION AND AI APPLICATIONS                                              9 

First Order Predicate Logic – Prolog Programming – Unification – Forward ChainingBackward Chaining – Resolution – Knowledge Representation – Ontological Engineering- AI applications – Language Models – Information Retrieval- Information Extraction – Natural Language Processing – Machine Translation – Speech Recognition – Robot. 

UNIT IV MACHINE LEARNING AND SUPERVISED LEARNING ALGORITHMS                                               9 

Introduction to Machine Learning (ML) - Essential concepts of ML –Learning a Class from Examples- Linear, Non-linear-Multi-class and Multi-label classification-Decision Trees- ID3-Classification and Regression Trees (CART)-Regression- Linear RegressionMultiple Linear Regression- Logistic Regression- Bayesian Classifier- Bayesian Network. 

UNIT V UNSUPERVISED LEARNING AND NEURAL NETWORKS                                9 

Introduction to clustering, clustering algorithms - Self-Organizing Map - Expectation Maximization - Gaussian Mixture Models – Principal Component Analysis (PCA) - Basic Neural Networks: Concept of Neurons - Perceptron Algorithm - Feed forward and Back Propagation Networks.